fix(monitoring): use storage aligned with azure storage tier

thenav56 · thenav56 · commit 341e199d09ee · 2026-04-01T17:09:29.000+05:45
remove day retention from prometheus
diff --git a/applications/argocd/production/platform/monitoring/kube-prometheus-stack.yaml b/applications/argocd/production/platform/monitoring/kube-prometheus-stack.yaml
@@ -71,14 +71,13 @@ spec:
           prometheusSpec:
             # TODO: Increase/decrease as needed
             # https://prometheus.io/docs/prometheus/latest/storage/#right-sizing-retention-size
-            retention: 90d  # How long to retain metrics
-            retentionSize: "18GB"  # Maximum size of metrics
+            retentionSize: "20GB"  # Maximum size of metrics
             storageSpec:
               volumeClaimTemplate:
                 spec:
                   resources:
                     requests:
-                      storage: 20Gi
+                      storage: 32Gi  # Cost is defined at tier level
 
         # TODO: Enable and configure this
         alertmanager:
diff --git a/applications/argocd/production/platform/monitoring/loki.yaml b/applications/argocd/production/platform/monitoring/loki.yaml
@@ -85,7 +85,7 @@ spec:
             enabled: true
             persistence:
               enabled: true
-              size: 20Gi
+              size: 32Gi  # Cost is defined at tier level
 
           # Zero out replica counts of other deployment modes
           backend:
diff --git a/applications/argocd/staging/platform/monitoring/kube-prometheus-stack.yaml b/applications/argocd/staging/platform/monitoring/kube-prometheus-stack.yaml
@@ -71,14 +71,13 @@ spec:
           prometheusSpec:
             # TODO: Increase/decrease as needed
             # https://prometheus.io/docs/prometheus/latest/storage/#right-sizing-retention-size
-            retention: 90d  # How long to retain metrics
-            retentionSize: "18GB"  # Maximum size of metrics
+            retentionSize: "20GB"  # Maximum size of metrics
             storageSpec:
               volumeClaimTemplate:
                 spec:
                   resources:
                     requests:
-                      storage: 20Gi
+                      storage: 32Gi  # Cost is defined at tier level
 
         # TODO: Enable and configure this
         alertmanager:
diff --git a/applications/argocd/staging/platform/monitoring/loki.yaml b/applications/argocd/staging/platform/monitoring/loki.yaml
@@ -85,7 +85,7 @@ spec:
             enabled: true
             persistence:
               enabled: true
-              size: 20Gi
+              size: 32Gi  # Cost is defined at tier level
 
           # Zero out replica counts of other deployment modes
           backend:
